CCSpO2Net: Camera-Based Contactless Oxygen Saturation Measurement Foundation Model in Clinical Settings

Oxygen saturation (SpO2) is a vital parameter in clinical practice. Clinical research suggests that SpO2 may significantly decrease in patients with lung infections before evident symptoms, such as COVID-19, appear. Therefore, monitoring the cardiopulmonary status of individuals with lung disease is indispensable. Although contactless SpO2 measurements perform well in laboratory settings, their clinical application still faces several challenges. To bridge this gap, a camera-based contactless SpO2 measurement foundation model called CCSpO2Net is proposed, which is appropriate for both clinical and laboratory settings. This approach is based on a spatial feature extractor (SFE) and a global temporal feature extractor and estimator (GTFEE). The SFE employs two residual networks to enhance interchannel correlations and capture spatial information. The GTFEE module consists of a multilayer perceptron mixer (MLP-Mixer) network and an SpO2 estimator. The MLP-Mixer operation facilitates global temporal information exchange across positions by rearranging and swapping the features along the channel dimension. Additionally, the segment anything model (SAM) was first utilized to accurately extract skin regions at the pixel level to measure SpO2. Finally, we are the first to explore the topic of contactless SpO2 estimation based on facial videos in a clinical environment; remarkable results were achieved, with a mean absolute error (MAE) of 1.79 and a root-mean-square error (RMSE) of 2.85 on the intensive care unit (ICU) dataset. Moreover, the extensive experimental results further validate that CCSpO2Net outperforms the state-of-the-art approaches significantly, achieving MAEs of 0.54 (improved by 16.7%) and 2.48 (improved by 101.6%) on the PURE and smartphone camera oximetry (SCO) datasets, respectively.